Sparse Autoencoder for Mechanistic Interpretability
☆308Jul 20, 2024Updated 2 years ago
Alternatives and similar repositories for sparse_autoencoder
Users that are interested in sparse_autoencoder are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Using sparse coding to find distributed representations used by neural networks.☆315Nov 10, 2023Updated 2 years ago
- ☆142Oct 28, 2023Updated 3 years ago
- Training Sparse Autoencoders on Language Models☆1,579Oct 20, 2026Updated 2 weeks ago
- ☆610Jul 19, 2024Updated 2 years ago
- Sparsify transformers with SAEs and transcoders☆742Updated this week
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆277Feb 27, 2026Updated 8 months ago
- Sparse Autoencoder Training Library☆59May 1, 2025Updated last year
- ☆435Aug 21, 2025Updated last year
- A quick way to get started with Transformer Lens☆15Dec 13, 2023Updated 2 years ago
- ☆225Oct 14, 2025Updated last year
- A library for mechanistic interpretability of GPT-style language models☆4,031Updated this week
- ☆62Nov 19, 2024Updated last year
- ☆186May 1, 2026Updated 6 months ago
- Mechanistic Interpretability Visualizations using React☆372Apr 30, 2026Updated 6 months ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆301Oct 1, 2024Updated 2 years ago
- Decoder only transformer, built from scratch with PyTorch☆34Oct 22, 2023Updated 3 years ago
- A framework for training, analyzing, and visualizing sparse autoencoders and related interpretability methods☆232Oct 4, 2026Updated 3 weeks ago
- Easy training for Sparse Linear Autoencoders (https://arxiv.org/abs/2309.08600) with data from TransformerLens models.☆12Nov 1, 2023Updated 3 years ago
- Sparse probing paper full code.☆69Dec 17, 2023Updated 2 years ago
- A very hacky set of functions for getting plotly to do what I want when doing mech interp research, designed to be compatible with PyTorc…☆16Jun 16, 2023Updated 3 years ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated 2 years ago
- ☆26Dec 20, 2023Updated 2 years ago
- ☆214Nov 17, 2024Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- The nnsight package enables interpreting and manipulating the internals of deep learned models.☆1,138Updated this week
- A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations☆17Apr 15, 2024Updated 2 years ago
- A curated list of LLM Interpretability related material - Tutorial, Library, Survey, Paper, Blog, etc..☆308Jan 22, 2026Updated 9 months ago
- Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons☆15Feb 13, 2023Updated 3 years ago
- ☆113May 23, 2026Updated 5 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆34May 23, 2024Updated 2 years ago
- ☆32Apr 4, 2024Updated 2 years ago
- ☆1,084Mar 6, 2024Updated 2 years ago
- Code Release for the 2023 NeurIPS Paper How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained langua…☆17Dec 6, 2024Updated last year
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Tools for understanding how transformer predictions are built layer-by-layer☆619Aug 7, 2025Updated last year
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆61Nov 3, 2024Updated last year
- ☆38Apr 30, 2024Updated 2 years ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆158Sep 14, 2022Updated 4 years ago
- Code for 'The Linear Representation Hypothesis and the Geometry of Large Language Models' (ICML 2024)☆135Feb 11, 2025Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆259May 23, 2024Updated 2 years ago
- Stanford NLP Python library for understanding and improving PyTorch models via interventions☆914Mar 6, 2026Updated 7 months ago